Re-implememtation of MAE (Masked Autoencoders Are Scalable Vision Learners) using PyTorch.

Related tags

Deep Learningmae-repo
Overview

mae-repo

PyTorch re-implememtation of "masked autoencoders are scalable vision learners". In this repo, it heavily borrows codes from codebase https://github.com/lucidrains/vit-pytorch (for MAE architectures) and https://github.com/pengzhiliang/MAE-pytorch (for training loop).

prepare ImageNet1K datasets

To train MAE, one should prepare ImageNet_ILSVRC2012 and place ILSVRC2012_*.tar in the ${datasets_path}. To shorten the overhead of first run, one can manually untar the tarfile into train and val directories, as follow (refered to https://gist.github.com/BIGBALLON/8a71d225eff18d88e469e6ea9b39cef4).

mkdir train && mv ILSVRC2012_img_train.tar train/ && cd train
tar -xvf ILSVRC2012_img_train.tar && rm -f ILSVRC2012_img_train.tar
find . -name "*.tar" | while read NAME ; do mkdir -p "${NAME%.tar}"; tar -xvf "${NAME}" -C "${NAME%.tar}"; rm -f "${NAME}"; done
cd ..
mkdir val && mv ILSVRC2012_img_val.tar val/ && cd val && tar -xvf ILSVRC2012_img_val.tar
wget -qO- https://raw.githubusercontent.com/soumith/imagenetloader.torch/master/valprep.sh | bash

modify configuration file

To separate code and config, we try to split configurations to yaml file, located in configs directory, such as imagenet1k-vit-base.yml. One can modify 'model' setting following MAE and ViT to configure model architecture parameters of ViT-base, large and huge.

One can modify 'optim' for optimizer settings. And modify 'training' and 'data' for training settings. Note that, modify 'training:batch_size' to fit the GPU memory of one GPU card. Total batch_size is equal to batch_size multiplied by number of GPU cards.

train

CUDA_VISIBLE_DEVICES=0,1,2,3,5,6,7 OMP_NUM_THREADS=1 python -m torch.distributed.launch --nproc_per_node=8 mae_test.py
--datasets_path ${datasets_path}
--config imagenet1k-vit-base.yml
--doc mae-vit-base16-dec8-512

ToDo lists

  • add pretrain mode
  • add fine-tunning mode
  • support mixed precision training
  • support distributed training
  • verify the correctness of this re-implementation
Owner
Peng Qiao
Peng Qiao
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Tensor2Tensor Tensor2Tensor, or T2T for short, is a library of deep learning models and datasets designed to make deep learning more accessible and ac

12.9k Jan 09, 2023
Extending JAX with custom C++ and CUDA code

Extending JAX with custom C++ and CUDA code This repository is meant as a tutorial demonstrating the infrastructure required to provide custom ops in

Dan Foreman-Mackey 237 Dec 23, 2022
Flexible Option Learning - NeurIPS 2021

Flexible Option Learning This repository contains code for the paper Flexible Option Learning presented as a Spotlight at NeurIPS 2021. The implementa

Martin Klissarov 7 Nov 09, 2022
Split your patch similarly to `git add -p` but supporting multiple buckets

split-patch.py This is git add -p on steroids for patches. Given a my.patch you can run ./split-patch.py my.patch You can choose in which bucket to p

102 Oct 06, 2022
Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"

BEGAN in Tensorflow Tensorflow implementation of BEGAN: Boundary Equilibrium Generative Adversarial Networks. Requirements Python 2.7 or 3.x Pillow tq

Taehoon Kim 922 Dec 21, 2022
ICLR21 Tent: Fully Test-Time Adaptation by Entropy Minimization

⛺️ Tent: Fully Test-Time Adaptation by Entropy Minimization This is the official project repository for Tent: Fully-Test Time Adaptation by Entropy Mi

Dequan Wang 204 Dec 25, 2022
EmoTag helps you train emotion detection model for Chinese audios

emoTag emoTag helps you train emotion detection model for Chinese audios. Environment pip install -r requirement.txt Data We used Emotional Speech Dat

_zza 4 Sep 07, 2022
A framework for using LSTMs to detect anomalies in multivariate time series data. Includes spacecraft anomaly data and experiments from the Mars Science Laboratory and SMAP missions.

Telemanom (v2.0) v2.0 updates: Vectorized operations via numpy Object-oriented restructure, improved organization Merge branches into single branch fo

Kyle Hundman 844 Dec 28, 2022
Combinatorially Hard Games where the levels are procedurally generated

puzzlegen Implementation of two procedurally simulated environments with gym interfaces. IceSlider: the agent needs to reach and stop on the pink squa

Autonomous Learning Group 3 Jun 26, 2022
Official PyTorch Implementation for "Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes"

PVDNet: Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes This repository contains the official PyTorch implementatio

Junyong Lee 98 Nov 06, 2022
1st place solution to the Satellite Image Change Detection Challenge hosted by SenseTime

1st place solution to the Satellite Image Change Detection Challenge hosted by SenseTime

Lihe Yang 209 Jan 01, 2023
Weakly-supervised semantic image segmentation with CNNs using point supervision

Code for our ECCV paper What's the Point: Semantic Segmentation with Point Supervision. Summary This library is a custom build of Caffe for semantic i

27 Sep 14, 2022
PED: DETR for Crowd Pedestrian Detection

PED: DETR for Crowd Pedestrian Detection Code for PED: DETR For (Crowd) Pedestrian Detection Paper PED: DETR for Crowd Pedestrian Detection Installati

36 Sep 13, 2022
Simulate genealogical trees and genomic sequence data using population genetic models

msprime msprime is a population genetics simulator based on tskit. Msprime can simulate random ancestral histories for a sample of individuals (consis

Tskit developers 150 Dec 14, 2022
Instance-wise Occlusion and Depth Orders in Natural Scenes (CVPR 2022)

Instance-wise Occlusion and Depth Orders in Natural Scenes Official source code. Appears at CVPR 2022 This repository provides a new dataset, named In

27 Dec 27, 2022
[NeurIPS 2021] Garment4D: Garment Reconstruction from Point Cloud Sequences

Garment4D [PDF] | [OpenReview] | [Project Page] Overview This is the codebase for our NeurIPS 2021 paper Garment4D: Garment Reconstruction from Point

Fangzhou Hong 112 Dec 23, 2022
🔊 Audio and fastai v2

Fastaudio An audio module for fastai v2. We want to help you build audio machine learning applications while minimizing the need for audio domain expe

152 Dec 28, 2022
EsViT: Efficient self-supervised Vision Transformers

Efficient Self-Supervised Vision Transformers (EsViT) PyTorch implementation for EsViT, built with two techniques: A multi-stage Transformer architect

Microsoft 352 Dec 25, 2022
Multi-scale discriminator feature-wise loss function

Multi-Scale Discriminative Feature Loss This repository provides code for Multi-Scale Discriminative Feature (MDF) loss for image reconstruction algor

Graphics and Displays group - University of Cambridge 76 Dec 12, 2022
PyExplainer: A Local Rule-Based Model-Agnostic Technique (Explainable AI)

PyExplainer PyExplainer is a local rule-based model-agnostic technique for generating explanations (i.e., why a commit is predicted as defective) of J

AI Wizards for Software Management (AWSM) Research Group 14 Nov 13, 2022